Measure a server's MCP Tasks durability instead of trusting its declarations.
MCP Tasks promise a durable handle for long-running work, but compliance is not durability: a server on an in-memory backend passes conformance and loses every task on a routine restart, a crashed client leaves expensive work running unseen, and the protocol does not even require idempotent creation. This product measures a server's durability - create, TTL declaration, TTL honesty re-read inside the window, reconnect, retry-dedup, era-tagged rediscovery, cancel support verified by observation - and publishes DURABLE / FRAGILE / ORPHAN-RISK / UNMEASURED-RESTART / UNTESTED / NOT-A-TASKS-SERVER per server, with a fleet task ledger that inventories every taskId across your servers and a reaper that cancels confirmed orphans with a receipt and reports the un-cancellable ones with their burn instead of dropping them silently. The API verdict is reconnect-only and UNMEASURED-RESTART is provisional; restart legs run only through an operator-supplied restart callback against the operator's own staging/shadow or scheduled instances. Live-egress probe cost was measured at ship time against a live fixture reached over the public network path and is recorded in the ship report.
Prices: Per-server durability verdict $0.25/server/mo (x402) · Fleet task ledger + orphan reaper $19/mo (up to 50 servers) · Registry / platform verdict feed $99/mo. One-time trial: the first server's first durability verdict is free, once per operator account AND per payer wallet; there is no perpetual free tier.
Start: POST /register {"name", "payer_wallet"} → POST /trial/claim {"claim_token"} returns your API token; then POST /verdict with Bearer auth. Docs at /docs, OpenAPI at /openapi.json, x402 discovery at /.well-known/x402.
Support: support@textforagents.com · Terms: /terms · Privacy: /privacy